HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Platypus2-70B-Instruct-GPTQ

TheBloke/Platypus2-70B-Instruct-GPTQ

kind
gptq
quant
gptq
family
misc
modality
text-generation
root model
garage-bAInd/Platypus2-70B-instruct
provider
TheBloke
license
cc-by-nc-4.0
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
46
likes
25
created
—
last modified
2023-09-27T12:45:39+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Platypus2-70B-Instruct-GPTQ
tags
transformerssafetensorsllamatext-generationendataset:garage-bAInd/Open-Platypusdataset:Open-Orca/OpenOrcaarxiv:2308.07317arxiv:2307.09288base_model:garage-bAInd/Platypus2-70B-instructbase_model:quantized:garage-bAInd/Platypus2-70B-instructlicense:cc-by-nc-4.0text-generation-inference4-bitgptqregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge87.94HellaSwag (10-shot)medium| HellaSwag (10-shot) | 87.94 |
MMLUknowledge70.48MMLU (5-shot)medium| MMLU (5-shot) | 70.48 |
TruthfulQAsafety62.26TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 62.26 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.